Diabetic retinopathy techniques in retinal images: A review
作者：
Highlights：
• The algorithms for diabetic retinopathy was analyzed from year 2010 to 2018.
• The optic disc, blood vessel localization and segmentation are important for many features such as area, length, branching angle, perimeter of blood vessels and glaucoma. Therefore, these methods are represented in a separate section.
• The algorithms are classified into features for DR and classification of DR.
• This review is helpful to point out the missing area for research in medical images such as preprocessing, databases analyzed, application of mathematical morphology, etc.
摘要
•The algorithms for diabetic retinopathy was analyzed from year 2010 to 2018.•The optic disc, blood vessel localization and segmentation are important for many features such as area, length, branching angle, perimeter of blood vessels and glaucoma. Therefore, these methods are represented in a separate section.•The algorithms are classified into features for DR and classification of DR.•This review is helpful to point out the missing area for research in medical images such as preprocessing, databases analyzed, application of mathematical morphology, etc.
论文关键词：Computer aided diagnosis,Optic disc,Blood vessels,Exudates,Diabetic retinopathy screening
论文评审过程：Received 26 January 2018, Revised 8 October 2018, Accepted 24 October 2018, Available online 16 November 2018, Version of Record 13 June 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2018.10.009
